Back to skill

Security audit

Salesforce Reporting Copilot

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Salesforce reporting helper that uses disclosed, read-oriented Salesforce CLI commands, with a privacy caution around CRM data and local exports.

Install only if you are comfortable letting the agent guide Salesforce CLI commands against an org you choose. Prefer a sandbox or least-privilege Salesforce user for exploration, review SOQL before running it, and avoid saving schema or query outputs locally when they may contain sensitive business or personal data.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This markdown file includes commands that export object descriptions to a file and query Salesforce records, which can surface or persist potentially sensitive CRM metadata or data. The reference presents these operations as routine examples but does not warn users about handling production data, local file storage, or privacy implications.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.